How Google Maps uses AI to predict traffic and determine routes
According to Google, over 1 billion kilometers are driven with Google Maps in more than 220 countries and territories around the world every day. Google says behind scenes of offering satellite imagery, aerial photography, street maps, 360° interactive panoramic views of streets, real-time traffic conditions, and route planning for traveling by foot, car, bicycle, and air, or public transportation, there is so much that happens to deliver this information in a matter of seconds.
This reminds me of a Berlin-based artist who caused a virtual traffic nightmare in the streets in February. Simon Weckert, in what he termed as “Google Maps Hacks” pulled a little red wagon packed with 99 smartphones on the streets of Berlin to demonstrate the ubiquitous, real-life influence of modern technology. In a video he shared on his YouTube channel, as he wandered down the empty street it would go from green to orange to red on Google Maps, signaling of heavy traffic congestion. By the way, we can’t ignore the fact that Simon walked through the entire streets without getting mugged of his precious gadgets. Would you mind trying that in Moi Avenue, Nairobi?
He said he got the idea after going to a May Day demonstration in Berlin and noticed that Google Maps portrayed the gathering of people as a traffic jam. I’m not sure why Google assumes any phone that has allowed Google Maps on the street is of a driver inside a vehicle, it could be a group of people, nonetheless, nobody wants a route that is crowded, so the data is still useful, anyway.
Last week, Google shared how it uses artificial intelligence on Google Maps to predict the traffic situations and help advise its users on the best routes they should take. Google said when people navigate with Google Maps, their aggregate location data can be used to understand traffic conditions on roads all over the world. Google Maps analyzes historical traffic patterns for roads over time and combine these databases with live traffic conditions using machine learning to generate predictions based on both sets of data.
The tech giant said it recently partnered with DeepMind, an Alphabet AI research lab, to improve the accuracy of the traffic prediction capabilities and cut the inaccuracies by further using a machine learning architecture known as Graph Neural Networks that allows the two partners to conduct ‘spatiotemporal reasoning by incorporating relational learning biases to model the connectivity structure of real-world road networks’ to enable Google Maps to better predict whether or not you’ll be affected by a slowdown that ‘may not have even started yet’.
“Since the start of the COVID-19 pandemic, traffic patterns around the globe have shifted dramatically. We saw up to a 50 percent decrease in worldwide traffic when lockdowns started in early 2020,” Johann Lau, Product Manager at Google Maps said in a blog post.
“Since then, parts of the world have reopened gradually, while others maintain restrictions. To account for this sudden change, we’ve recently updated our models to become more agile—automatically prioritizing historical traffic patterns from the last two to four weeks, and deprioritizing patterns from any time before that,” he wrote.
Google Maps predictive traffic models play a key role in determining driving routes. If it predicts that traffic is likely to become heavy in one direction, it automatically finds you a lower-traffic alternative, while taking into consideration a number of other factors, like road quality and the size and directness of a road.
Authoritative data from local governments and real-time feedback from users also helps Google recommend the best routes for you. Data about speed limits, tolls, or if certain roads are restricted due to things like construction and incident reports from drivers let Google Maps quickly show if a road or lane is closed, if there’s construction nearby, or if there’s a disabled vehicle or an object on the road. Both sources are also used to understand when road conditions change unexpectedly due to factors such as mudslides, snowstorms, or other forces of nature.
Through these traffic predictions combined with live traffic conditions, Google automatically reroutes users using its knowledge about nearby road conditions and incidents to help them avoid the jam altogether and get to their destinations on time. Google says it will keep working on tools and technology to ensure its prediction on traffic and determining of routes, give its users safe, efficient, and reliable real-time data.